purewater0901

ray

Ray is a unified framework for scaling AI and Python applications. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.

autoware

Autoware - the world's leading open-source software project for autonomous driving

stable-baselines3

PyTorch version of Stable Baselines, reliable implementations of reinforcement learning algorithms.

Deep-reinforcement-learning-with-pytorch

PyTorch implementation of DQN, AC, ACER, A2C, A3C, PG, DDPG, TRPO, PPO, SAC, TD3 and ....

slam

learning SLAM,curse,paper and others

TD3

Author's PyTorch implementation of TD3 for OpenAI gym tasks

d3rlpy

An offline deep reinforcement learning library

CORL

High-quality single-file implementations of SOTA Offline and Offline-to-Online RL algorithms: AWAC, BC, CQL, DT, EDAC, IQL, SAC-N, TD3+BC, LB-SAC, SPOT, Cal-QL, ReBRAC

waymax

A JAX-based simulator for autonomous driving research.

pytorch-soft-actor-critic

PyTorch implementation of soft actor critic

metadrive

MetaDrive: Open-source driving simulator

ukf

Unscented Kalman Filter library for state and parameter estimation

deep-learning-from-scratch-4

『ゼロから作る Deep Learning ❹』(O'Reilly Japan, 2022)

trajdata

A unified interface to many trajectory forecasting datasets.

tdmpc2

Code for "TD-MPC2: Scalable, Robust World Models for Continuous Control"

deep-learning-from-scratch-5

『ゼロから作る Deep Learning ❺』(O'Reilly Japan, 2024)

traffic-behavior-simulation

homework_fall2023

IDQL

Repo for Implicit Diffusion Q-Learning

proj-svg_mppi

[ICRA2024] Stein Variational Guided Model Predictive Path Integral Control: Proposal and Experiments with Fast Maneuvering Vehicles

ReBRAC

Author's implementation of ReBRAC, a minimalist improvement upon TD3+BC

MCQ

Code for Mildly Conservative Q-learning for Offline Reinforcement Learning (NeurIPS 2022)

DOGE

The official implementation of "When Data Geometry Meets Deep Function: Generalizing Offline Reinforcement Learning" (ICLR2023)

Non-Gaussian_Risk-Bounded_TrajOpt

Non-Gaussian Risk Bounded Trajectory Optimization for StochasticNonlinear Systems in Uncertain Environments

geometric-parallel-parking

Geometric path planning for automatic parallel parking

mppi_playground

Model Predictive Path Integral Control (MPPI) with PyTorch

ReBRAC

Author's implementation of ReBRAC, a minimalist improvement upon TD3+BC

algebraic_moments

CPP_Convex_Hulls

This Git repository provides functionality for processing and manipulating Convex Hulls. The code can parse a JSON file containing Convex Hulls data and eliminate overlapping Convex Hulls based on a user-defined overlap threshold. The resulting Convex Hulls are then written to a new JSON file.

231b_project